---
title: "Discussion on \"Two From-Scratch Systems, and the Day They Talked\" | Hashnode"
description: "Discussion on \"Two From-Scratch Systems, and the Day They Talked\". I built a vector database and an LLM inference engine, each without leaning on someone else's runtime. This is the demo where they finally talked to each other — and the two real bugs that showed up doing it."
url: "https://hashnode.com/posts/two-from-scratch-systems-and-the-day-they-talked/6a9c5c43ad3755e014f0cf68"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Two From-Scratch Systems, and the Day They Talked](https://amankarki.hashnode.dev/two-from-scratch-systems-and-the-day-they-talked?utm_source=hashnode&utm_medium=feed)

I built a vector database and an LLM inference engine, each without leaning on someone else's runtime. This is the demo where they finally talked to each other — and the two real bugs that showed up doing it.

Sep 5 · 5 min read · amankarki.hashnode.dev  
Read the article

-   [#cpp](https://hashnode.com/tag/cpp)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#llm](https://hashnode.com/tag/llm)
-   [#system-programming](https://hashnode.com/tag/system-programming)
-   [#vector-database](https://hashnode.com/tag/vector-database)

## Written by

[Aman Karki](https://hashnode.com/@amankarki)

@amankarki · India

  
[View profile](https://hashnode.com/@amankarki)

C++/CUDA Engineer · LLM Inference & Systems

C++/CUDA engineer building LLM inference and GPU code from scratch: verbum.cpp, Lattice, RAAG. 2 CUDA PRs merged into llama.cpp. I write about inference, GPU performance, and measuring things honestly.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.